An evolutionary computing approach to minimize dynamic hedging error

The objective of our present paper is to derive a computationally efficient genetic pattern learning algorithm to evolutionarily derive the optimal rebalancing weights (i.e. dynamic hedge ratios) to engineer a structured financial product out of a multiasset, best-of option. The stochastic target function is formulated as an expected squared cost of hedging (tracking) error which is assumed to be partly dependent on the governing Markovian process underlying the individual asset returns and partly on
randomness i.e. pure white noise. A simple haploid genetic algorithm is advanced as an alternative numerical scheme, which is deemed to be
computationally more efficient than numerically deriving an explicit solution to the formulated optimization model. An extension to our proposed scheme is suggested by means of adapting the Genetic Algorithm parameters based on fuzzy logic controllers.

Lost at sea: genetic, oceanographic and meteorological evidence for storm-forced dispersal

For many species, there is broad-scale dispersal of juvenile stages and/or long-distance migration of individuals and hence the processes that drive these various wide-ranging movements have important life-history consequences. Sea turtles are one of these paradigmatic long-distance travellers, with hatchlings thought to be dispersed by ocean currents and adults often shuttling between distant breeding and foraging grounds. Here, we use multi-disciplinary oceanographic, atmospheric and genetic mixed stock analyses to show that juvenile turtles are encountered ‘downstream’ at sites predicted by currents. However, in some cases, unusual occurrences of juveniles are more readily explained by storm events and we show that juvenile turtles may be displaced thousands of kilometres from their expected dispersal based on prevailing ocean currents. As such, storms may be a route by which unexpected areas are encountered by juveniles which may in turn shape adult migrations. Increased stormy weather predicted under climate change scenarios suggests an increasing role of storms in dispersal of sea turtles and other marine groups with life-stages near the ocean surface.

A modified fuzzy min-max neural network with a genetic-algorithm-based rule extractor for pattern classification

In this paper, a two-stage pattern classification and rule extraction system is proposed. The first stage consists of a modified fuzzy min-max (FMM) neural-network-based pattern classifier, while the second stage consists of a genetic-algorithm (GA)-based rule extractor. Fuzzy if-then rules are extracted from the modified FMM classifier, and a ??don't care?? approach is adopted by the GA rule extractor to minimize the number of features in the extracted rules. Five benchmark problems and a real medical diagnosis task are used to empirically evaluate the effectiveness of the proposed FMM-GA system. The results are analyzed and compared with other published results. In addition, the bootstrap hypothesis analysis is conducted to quantify the results of the medical diagnosis task statistically. The outcomes reveal the efficacy of FMM-GA in extracting a set of compact and yet easily comprehensible rules while maintaining a high classification performance for tackling pattern classification tasks.

Fuzzy ARTMAP and a hybrid chaos genetic algorithm for medical pattern classification

In this paper, an Evolutionary Artificial Neural Network (EANN), which combines the Fuzzy ARTMAP (FAM) neural network and a hybrid Chaos Genetic Algorithm (CGA), is proposed for undertaking pattern classification tasks. The hybrid CGA is a modified version of the hybrid real-coded genetic algorithms that includes a Chaotic Mapping Operator (CMO) in its search and adaptation process. It is used to evolve the connection weights in FAM, and the resulting EANN is known as FAM-hybrid CGA. The CMO in the hybrid CGA is used to generate a group of chromosomes that incorporates the characteristics of chaos. The chromosomes are then adapted with an arbitrary small amount of variation in every generation. As the evolution procedure proceeds, chromosomes with considerable differences are produced. Such chromosomes, which are located at different regions of interest in the solution space, are able to provide good solutions to undertake search and adaption problems. The effectiveness of the proposed FAM-hybrid CGA model is first evaluated using benchmark medical data sets from the UCI machine learning repository. Its applicability to medical decision support is then demonstrated using a real database of patient records with suspected Acute Coronary Syndrome. The results indicate that FAM-hybrid CGA is able to outperform its neural network counterpart (i.e., FAM), and it can be employed as a useful pattern classification tool for tackling medical decision support tasks.

Life in the really slow lane : loggerhead sea turtles mature late relative to other reptiles

1. Age at maturity is hard to estimate for species that cannot be directly marked or observed throughout their lives and yet is a key demographic parameter that is needed to assess the conservation status of endangered species. 2. For loggerhead turtles (Caretta caretta) in the North Atlantic and North Pacific, juvenile growth rates (c. 10 cm year−1) were calculated by examining size increases during transoceanic journeys; durations of which were estimated from satellite-tracked Lagrangian surface drifter buoy trajectories. 3. Lagrangian-derived growth estimates were used in a weighted loglinear model of size-specific growth rates for loggerhead turtles and combined with newly available information on size at maturity to estimate an age at maturity of 45 years (older than past estimates). 4. By examining the age at maturity for 79 reptile species, we show that loggerhead turtles, along with other large-bodied Testudine (turtle and tortoise) species, take longer to reach maturity than other reptile species of comparable sizes. This finding heightens concern over the future sustainability of turtle populations. By maturing at an old age, sea turtles will be less resilient to anthropogenic mortality than previously suspected.

Thermal conductivity of sand and its effect on the temperature of Loggerhead Sea Turtle (Caretta Caretta) nests

The conductivity of sand at a depth of 30–50 cm was measured at 15 sites on the beach at Captiva Island in south-west Florida which is used by nesting loggerhead turtles (Caretta caretta). The mean daily temperature of the sand was correlated with conductivity at the same depth measured the same day (r=0·611). When day to day variation was removed the correlation between nest temperature and conductivity increased to 0·694. The sand was highly variable in its grain structure. The dominant variability (80·6%) was redescribed by the first two principal components of a Principal Components Analysis (PCA). These two components were influenced mostly by percentages of large (> 1 mm) and small (< 500 μm) grains respectively. Conductivity was strongly correlated with the grain structure of the sand. The first three principal components describing sand grain structure, explained 84·1% of the variation in conductivity. Moisture content of the sand (always < 5%) was not an important factor. Sites dominated by larger grains generally had poorer conductivity and were cooler. Comparisons of eight nests to seven adjacent random sites revealed no strong evidence for directional selection in nest placement relative to sand conductivity. The variance in conductivities recorded at nests was also not significantly different from the variance at random sites.

Estimating the age of juvenile loggerhead sea turtles in the North Atlantic

Analysis of previously published records shows that the modal size of juvenile loggerhead sea turtles (Caretta caretta) found around the United Kingdom (the area north of 49°N and east of 12°W) is a carapace length of 20.5 cm. These turtles are believed to originate from nesting beaches in North America (principally Florida). We estimated their trans-Atlantic drift time using data from satellite-tracked buoys and from a mathematical model and, hence, estimated that the modal age of these juvenile turtles was between 1.80 and 3.75 years.

Nest site selection by sea turtles

The distribution of 38 nests of loggerhead turtles (Caretta caretta) on beaches on Sanibel and Captiva islands, south-western Florida (26°26'N 82°16'W), and of 70 first digging attempts by green turtles (Chelonia mydas) on Ascension Island (7°57'S 14°22'W), was quantified. For loggerhead turtles on Sanibel and Captiva, nests were clumped close to the border between the open sand and the supra-littoral vegetation that backed the beaches. This spatial pattern of nests was closely reproduced by assuming simply that turtles crawled a random distance above the most recent high water line prior to digging. In contrast, green turtles on Ascension Island clumped their first digging attempts on the uneven beach above the springs high water line, crawling up to 80 m to reach this beach zone.

Reproductive investment and optimum clutch size of Loggerhead Sea Turtles (Caretta caretta)

(1) Data for loggerhead turtles (Caretta caretta L.) nesting on the Greek island of Cephalonia were used to develop a model which predicted the optimum clutch size. (2) There was a positive linear relationship between the number of clutches into which eggs could be divided and the total time spent by a nesting turtle on the beach, and hence a negative relationship between the time invested on the beach per egg and clutch size. (3) A previous study indicated that energy expenditure for nesting turtles on land is very high, so there may be a selective pressure to maximize clutch size in order to minimize the energy expended per egg laid. As there appeared to be no counterselective pressures favouring small clutches, clutch size should be constrained by a female's egg-carryingc apacity,w hich in turn could be expected to be related to her body size. Hence, a positive relationship between clutch size and body size was predicted, and was found in the population under study.

Fidelity to foraging sites, consistency of migration routes and habitat modulation of home range by sea turtles

Aim  Resources can shape patterns of habitat utilization. Recently a broad foraging dichotomy between oceanic and coastal sites has been revealed for loggerhead sea turtles (Caretta caretta). Since oceanic and coastal foraging sites differ in prey availability, we might expect a gross difference in home-range size across these habitats. We tested this hypothesis by equipping nine adult male loggerhead sea turtles with GPS tracking devices. Location  National Marine Park of Zakynthos (NMPZ) Greece, central and eastern Mediterranean (Adriatic, Ionian and Aegean seas). Methods  In 2007, 2008 and 2009, Fastloc GPS-Argos transmitters were attached to nine male loggerheads. In addition, a Sirtrack PTT unit was attached to one male in 2007. Four of the turtles were tracked on successive years. We filtered the GPS data to ensure comparable data volumes. Route consistency between breeding and foraging sites of the four re-tracked turtles was conducted. Foraging site home range areas and within site movement patterns were investigated by the fixed kernel density method. Results  Foraging home range size ranged between circa 10 km2 at neritic habitats (coastal and open-sea on the continental shelf) to circa 1000 km2 at oceanic sites (using 90% kernel estimates), the latter most probably reflecting sparsely distributed oceanic prey. Across different years individuals did not follow exactly the same migration routes, but did show fidelity to their previous foraging sites, whether oceanic or neritic, with accurate homing in the final stages of migration. Main conclusions  The broad distribution and diverse life-history strategies of this population could complicate the identification of priority marine protected areas beyond the core breeding site.

Female–female aggression : structure of interaction and outcome in loggerhead sea turtles

Aggressive behaviour between females of the same species is not widely documented, particularly in marine vertebrates. During a 3 yr in-water survey at the temperate loggerhead sea turtle Caretta caretta breeding area of Zakynthos, Greece, female–female interactions comprised 4% of all female loggerhead sighting events (n = 60 out of 1449 events). Male–female interactions comprised an additional 4% of sighting events, while 92% were of solitary females. The structure of interactions was analysed for 58 of these sighting events, each lasting an average of 3.4 min (SD ± 1) and comprising a total of 3.1 h observation time. We found that interactions involved ritualized escalation in behaviour from passive threat displays (e.g. head–tail circling) to aggressive combat (e.g. sparring). We suggest that circling individuals evaluate opponent size, sparring individuals test opponent strength, and that the positioning of the prehensile tail signals motivational intent to either escalate or abort. The presence of intruder females triggered a passive response in 100% of events involving basking and swimming turtles (n = 19); although residents resting on the seabed only responded on 69% of occasions (n = 27), their response was almost 4 times more likely to escalate to one of aggression. Our results suggest that certain sites may be preferentially sought after and defended by sea turtles.

Population genetic studies on Australian freshwater crayfish, Cherax destructor (Crustacea: Parastacidae) using allozyme and RAPD markers

Allozyme and Random Amplified Polymorphic DNA (RAPD) variation was surveyed in the freshwater crayfish Cherax destructor Clark, an ecologically and commercially important species that is widespread throughout the freshwater systems of central Australia. At the intra-population level, allozymes revealed a similar level of variation to that found in other freshwater crayfish; RAPDs showed less diversity than allozymes, which was unexpected. At the inter-population level, both techniques revealed significant population structure, both within and between drainages. RAPD results were consistent with phylogeographic patterns previously identified using mtDNA. Although allozyme data showed little geographic pattern in relation to genetic variation based on multidimensional-scaling (MDS) plots on matrices of genetic distance, results of AMOVA and Mantel tests indicated significant population structuring. Each of the mtDNA lineages proposed in a previous study also showed significant genetic structure at similar levels as revealed by RAPDs but different levels by allozymes. These results reject hypotheses previously put forward on genetic homogenisation within the species due to wide-scale translocation. The implications of the findings for conservation and aquaculture of C. destructor are also discussed.

Evolution of egg size and fertilisation efficiency in sea stars: large eggs are not fertilised more readily than small eggs in Patiriella (Echinodermata: Asteroidea)

Fertilisation kinetics theory suggests that, when sperm are limiting, the larger eggs of broadcast-spawning marine organisms ought to be fertilised more frequently than smaller eggs, because they provide a bigger target for searching sperm. Whilst this effect has been demonstrated within species, it is not known if this pattern holds among species. We tested whether a large difference in egg size between congeneric seastars with contrasting planktotrophic and lecithotrophic modes of development results in differences in the likelihood of eggs being fertilised in sperm-limiting situations. Measurement of egg sizes and sperm swimming speeds led to the prediction that the sperm–egg collision rate constant for Patiriella calcar (420-µm-diameter egg) should be nine times greater than for P. regularis (140-µm-diameter egg). Although the eggs of P. calcar should be fertilised at greater rates in low sperm concentrations, they were not. When gametes were allowed to mix for 10 s, the hypothesis that P. calcar eggs required less sperm than P. regularis to ensure 50% of eggs were fertilised was rejected. When gametes were mixed for 5 min, P. regularis eggs were more frequently fertilised, but the difference was not statistically significant. We conclude there must be a difference between these species in the likelihood that when a sperm finds a conspecific egg it can successfully fertilise. This apparent uncoupling of egg size and likelihood of fertilisation suggests that fertilisation is not a major constraint on the evolution of egg size in these seastars.

The rough sets feature selection for trees recognition in color aerial images using genetic algorithms

Selecting a set of features which is optimal for a given task is the problem which plays an important role in a wide variety of contexts including pattern recognition, images understanding and machine learning. The concept of reduction of the decision table based on the rough set is very useful for feature selection. In this paper, a genetic algorithm based approach is presented to search the relative reduct decision table of the rough set. This approach has the ability to accommodate multiple criteria such as accuracy and cost of classification into the feature selection process and finds the effective feature subset for texture classification . On the basis of the effective feature subset selected, this paper presents a method to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The experiments results show that the feature subset selected and the method of the object extraction presented in this paper are practical and effective.